© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 82923
    Prev
    Next
    INDEX
    Explanations

    terms related to risk and risk management

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iska
    -0.07
    eyn
    -0.07
    imler
    -0.07
    aign
    -0.07
    coder
    -0.07
    eyer
    -0.07
    æ´¾
    -0.07
    íĴĪ
    -0.07
    ename
    -0.07
    اÙĩÛĮ
    -0.07
    POSITIVE LOGITS
     management
    0.09
     Management
    0.09
    er
    0.07
     Sext
    0.07
    ands
    0.07
    lessly
    0.07
     MANAGEMENT
    0.06
    -management
    0.06
    µľ
    0.06
    orado
    0.06
    Activations Density 0.005%

    No Known Activations